mlsanityData to 7 Oct 2026

Torchhd: An Open Source Python Library to Support Research on Hyperdimensional Computing and Vector Symbolic Architectures

arXiv 2205.09208 ↗First posted 18 May 2022cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

Hyperdimensional computing (HD), also known as vector symbolic architectures (VSA), is a framework for computing with distributed representations by exploiting properties of random high-dimensional vector spaces. The commitment of the scientific community to aggregate and disseminate research in this particularly multidisciplinary area has been fundamental for its advancement. Joining these efforts, we present Torchhd, a high-performance open source Python library for HD/VSA. Torchhd seeks to make HD/VSA more accessible and serves as an efficient foundation for further research and application development. The easy-to-use library builds on top of PyTorch and features state-of-the-art HD/VSA functionality, clear documentation, and implementation examples from well-known publications. Comparing publicly available code with their corresponding Torchhd implementation shows that experiments can run up to 100x faster. Torchhd is available at: https://github.com/hyperdimensional-computing/torchhd.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 23 of its 64 references that are in the map. First posted on arXiv 18 May 2022.

Builds on

23 of 64 references.

References · 23

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2020Hopfield Networks is All You Needcited by 461
  4. 2016Dense Associative Memory for Pattern Recognitioncited by 230
  5. 2020On the Binding Problem in Artificial Neural Networkscited by 230
  6. 2021A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformationscited by 98
  7. 2022Constrained Few-shot Class-incremental Learningcited by 93
  8. 2021A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challengescited by 68
  9. 2022A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matricescited by 64
  10. 2020A comparison of Vector Symbolic Architecturescited by 63
  11. 2020Classification using Hyperdimensional Computing: A Reviewcited by 60
  12. 2022Neurocompositional computing: From the Central Paradox of Cognition to a new generation of AI systemscited by 44
11 more
  1. 2021Computing on Functions Using Randomized Vector Representationscited by 41
  2. 2021Vector Symbolic Architectures as a Computing Framework for Emerging Hardwarecited by 35
  3. 2018A theory of sequence indexing and working memory in recurrent neural networkscited by 29
  4. 2022GraphHD: Efficient graph classification using hyperdimensional computingcited by 28
  5. 2020Variable Binding for Sparse Distributed Representations: Theory and Applicationscited by 27
  6. 2021Learning with Holographic Reduced Representationscited by 25
  7. 2019Density Encoding Enables Resource-Efficient Randomly Connected Neural Networkscited by 15
  8. 2021Generalized Learning Vector Quantization for Classification in Randomized Neural Networks and Hyperdimensional Computingcited by 12
  9. 2022Integer Factorization with Compositional Distributed Representationscited by 4
  10. 2022An Extension to Basis-Hypervectors for Learning from Circular Data in Hyperdimensional Computingcited by 4
  11. 2022Hyperdimensional Hashing: A Robust and Efficient Dynamic Hash Tablecited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 5; 2026: 4.

17 papers.

Sort:

  1. 2024A Walsh Hadamard Derived Linear Vector Symbolic Architecturecited by 4
  2. 2024HEAL: Brain-inspired Hyperdimensional Efficient Active Learningcited by 3
  3. 2024MicroHD: An Accuracy-Driven Optimization of Hyperdimensional Computing Algorithms for TinyML systemscited by 3
  4. 2025Hey Pentti, We Did It!: A Fully Vector-Symbolic Lispcited by 2
  5. 2024Molecular Classification Using Hyperdimensional Graph Classificationcited by 1
  6. 2024Enhanced Detection of Transdermal Alcohol Levels Using Hyperdimensional Computing on Embedded Devicescited by 1
  7. 2024DEBUG-HD: Debugging TinyML models on-device using Hyper-Dimensional computingcited by 1
  8. 2025Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architecturescited by 1
  9. 2025HYPERDOA: Robust and Efficient DoA Estimation using Hyperdimensional Computingcited by 1
  10. 2024CiliaGraph: Enabling Expression-enhanced Hyper-Dimensional Computation in Ultra-Lightweight and One-Shot Graph Classification on Edgecited by 0
  11. 2024Privacy-Preserving Federated Learning with Differentially Private Hyperdimensional Computingcited by 0
  12. 2025ScalableHD: Scalable and High-Throughput Hyperdimensional Computing Inference on Multi-Core CPUscited by 0
5 more
  1. 2025BiHDTrans: binary hyperdimensional transformer for efficient multivariate time series classificationcited by 0
  2. 2026hdlib 2.0: Extending Machine Learning Capabilities of Vector-Symbolic Architecturescited by 0
  3. 2026HyperSpace: A Generalized Framework for Spatial Encoding in Hyperdimensional Representationscited by 0
  4. 2026QeHDC: Hyperdimensional Computing based on Quantum-enhanced binding and SuperClass Constructioncited by 0
  5. 2026Compiler-Driven Approximation Tuning for Hyperdimensional Computingcited by 0